Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     też
    -0.08
     contienen
    -0.08
    elastic
    -0.07
    /display
    -0.07
    contains
    -0.07
     Comercio
    -0.07
     master
    -0.07
     contains
    -0.07
     והש
    -0.07
     từ
    -0.07
    POSITIVE LOGITS
    穴
    0.08
     doubtful
    0.08
     acquaintances
    0.08
     प्रत्य
    0.07
    	out
    0.07
     Bonn
    0.07
     മാറ
    0.07
    बाक
    0.07
    iseerd
    0.07
     домашних
    0.07
    Act Density 0.006%

    No Known Activations